include/uapi/linux/prctl.h | 1 + security/commoncap.c | 129 +++++++++++++++++++++++++++++++++++++ 2 files changed, 130 insertions(+)
The capability bounding set is per-thread: PR_CAPBSET_DROP only affects
the calling thread, since its bounding set lives in the per-task struct
cred. User space that wants to drop capabilities for a whole process
must therefore invoke PR_CAPBSET_DROP once per capability per thread,
which on a many-threaded process is expensive, and from a Go runtime
requires stopping the world and signalling every thread.
Add PR_CAPBSET_DROP_MASK, an opt-in prctl that removes a set of
capabilities, given as a 64-bit mask in arg2 (low 32 bits) and arg3
(high 32 bits), from the bounding set of every thread of the calling
thread group in a single call.
The calling thread drops the capabilities synchronously, last; every
sibling that still holds any of them is asked to drop them through a
task_work item, so that it applies the drop in its own context. This
avoids racing with a sibling's concurrent credential updates such as
setuid() or capset(). The call does not wait for the siblings: a
sibling may be parked in a wait that is not woken by TIF_NOTIFY_SIGNAL
(e.g. futex), so waiting could block for an unbounded time. This is
still safe, because TIF_NOTIFY_SIGNAL is handled on the way out to user
mode, so a sibling applies the drop before executing any further
userspace code. It does not synchronize against a sibling that is
concurrently creating threads, so callers must keep the thread group
quiescent while dropping.
Measured with gVisor's "bounding set trimmed" boot phase on an arm64 KVM
guest (medians over repeated boots):
- 8 vCPUs: ~1.6ms -> ~0.10ms
- 32 vCPUs: ~3.5ms -> ~0.11ms
- 64 vCPUs: ~10.1ms -> ~0.1-0.6ms
- cost goes from O(capabilities * threads) stop-the-world prctls to a
single thread-group walk.
Cc: Serge Hallyn <serge@hallyn.com>
Cc: Paul Moore <paul@paul-moore.com>
Cc: James Morris <jmorris@namei.org>
Cc: Paul Walmsley <pjw@kernel.org>
Cc: Thomas Gleixner <tglx@kernel.org>
Cc: Zong Li <zong.li@sifive.com>
Cc: Deepak Gupta <debug@rivosinc.com>
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
---
include/uapi/linux/prctl.h | 1 +
security/commoncap.c | 129 +++++++++++++++++++++++++++++++++++++
2 files changed, 130 insertions(+)
diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
index b6ec6f693719..750a7824d3bc 100644
--- a/include/uapi/linux/prctl.h
+++ b/include/uapi/linux/prctl.h
@@ -70,6 +70,7 @@
/* Get/set the capability bounding set (as per security/commoncap.c) */
#define PR_CAPBSET_READ 23
#define PR_CAPBSET_DROP 24
+#define PR_CAPBSET_DROP_MASK 83
/* Get/set the process' ability to use the timestamp counter instruction */
#define PR_GET_TSC 25
diff --git a/security/commoncap.c b/security/commoncap.c
index 3399535808fe..ae7ce50a8151 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -19,7 +19,14 @@
#include <linux/hugetlb.h>
#include <linux/mount.h>
#include <linux/sched.h>
+#include <linux/cred.h>
+#include <linux/rcupdate.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
+#include <linux/slab.h>
+#include <linux/task_work.h>
#include <linux/prctl.h>
+#include <linux/printk.h>
#include <linux/securebits.h>
#include <linux/user_namespace.h>
#include <linux/binfmts.h>
@@ -1283,6 +1290,123 @@ static int cap_prctl_drop(unsigned long cap)
return commit_creds(new);
}
+/*
+ * Structure used to queue process-wide bounding set drops via task_work.
+ */
+struct cap_bset_drop_work {
+ struct callback_head work;
+ struct task_struct *task;
+ kernel_cap_t mask;
+ struct cap_bset_drop_work *next;
+};
+
+static void cap_bset_drop_work_fn(struct callback_head *work)
+{
+ struct cap_bset_drop_work *w = container_of(work, struct cap_bset_drop_work, work);
+ struct cred *new = prepare_creds();
+
+ if (!new) {
+ /* Out of memory: bounding set drop failed silently for this thread. */
+ pr_warn_ratelimited("capability bounding set drop failed for pid %d (%s)\n",
+ task_pid_nr(current), current->comm);
+ goto out;
+ }
+
+ new->cap_bset = cap_drop(new->cap_bset, w->mask);
+ commit_creds(new);
+
+out:
+ put_task_struct(w->task);
+ kfree(w);
+}
+
+/*
+ * cap_bset_drop_process - Drop capabilities from all threads in the group.
+ * @mask: Mask of capabilities to drop from the bounding set.
+ *
+ * Drops @mask from the calling thread synchronously, and queues a task_work
+ * item for each sibling thread to safely apply the drop in its own context.
+ *
+ * The caller must hold CAP_SETPCAP. Thread group must be quiescent to avoid
+ * racing with concurrent thread creation.
+ *
+ * Returns 0 on success, or -ENOMEM if allocations fail (all-or-nothing).
+ */
+static int cap_bset_drop_process(kernel_cap_t mask)
+{
+ struct cap_bset_drop_work *list = NULL, *w, *next;
+ struct task_struct *thread;
+ struct cred *new = NULL;
+ int ret = 0;
+
+ rcu_read_lock();
+ for_each_thread(current, thread) {
+ const struct cred *cred;
+
+ if (thread == current || (thread->flags & PF_EXITING))
+ continue;
+
+ cred = __task_cred(thread);
+ if (cap_isclear(cap_intersect(cred->cap_bset, mask)))
+ continue;
+
+ w = kmalloc_obj(*w, GFP_ATOMIC);
+ if (!w) {
+ ret = -ENOMEM;
+ break;
+ }
+
+ w->task = get_task_struct(thread);
+ w->mask = mask;
+ w->next = list;
+ list = w;
+ }
+ rcu_read_unlock();
+
+ if (!ret) {
+ new = prepare_creds();
+ if (!new)
+ ret = -ENOMEM;
+ }
+
+ if (ret) {
+ while (list) {
+ next = list->next;
+ put_task_struct(list->task);
+ kfree(list);
+ list = next;
+ }
+ return ret;
+ }
+
+ for (w = list; w; w = next) {
+ next = w->next;
+ init_task_work(&w->work, cap_bset_drop_work_fn);
+ if (task_work_add(w->task, &w->work, TWA_SIGNAL)) {
+ put_task_struct(w->task);
+ kfree(w);
+ }
+ }
+
+ new->cap_bset = cap_drop(new->cap_bset, mask);
+ commit_creds(new);
+
+ return 0;
+}
+
+static int cap_prctl_drop_mask(unsigned long low, unsigned long high)
+{
+ kernel_cap_t mask = mk_kernel_cap((u32)low, (u32)high);
+
+ if (cap_isclear(mask))
+ return 0;
+
+ if (!ns_capable(current_user_ns(), CAP_SETPCAP))
+ return -EPERM;
+
+ return cap_bset_drop_process(mask);
+}
+
/**
* cap_task_prctl - Implement process control functions for this security module
* @option: The process control function requested
@@ -1313,6 +1437,11 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
case PR_CAPBSET_DROP:
return cap_prctl_drop(arg2);
+ case PR_CAPBSET_DROP_MASK:
+ if (arg4 || arg5)
+ return -EINVAL;
+ return cap_prctl_drop_mask(arg2, arg3);
+
/*
* The next four prctl's remain to assist with transitioning a
* system from legacy UID=0 based privilege (when filesystem
--
2.34.1On Tue, Sep 22, 2026 at 05:58:16PM +0800, Jinjie Ruan wrote:
> The capability bounding set is per-thread: PR_CAPBSET_DROP only affects
> the calling thread, since its bounding set lives in the per-task struct
> cred. User space that wants to drop capabilities for a whole process
> must therefore invoke PR_CAPBSET_DROP once per capability per thread,
> which on a many-threaded process is expensive, and from a Go runtime
> requires stopping the world and signalling every thread.
>
> Add PR_CAPBSET_DROP_MASK, an opt-in prctl that removes a set of
> capabilities, given as a 64-bit mask in arg2 (low 32 bits) and arg3
> (high 32 bits), from the bounding set of every thread of the calling
> thread group in a single call.
>
> The calling thread drops the capabilities synchronously, last; every
> sibling that still holds any of them is asked to drop them through a
> task_work item, so that it applies the drop in its own context. This
> avoids racing with a sibling's concurrent credential updates such as
> setuid() or capset(). The call does not wait for the siblings: a
> sibling may be parked in a wait that is not woken by TIF_NOTIFY_SIGNAL
> (e.g. futex), so waiting could block for an unbounded time. This is
> still safe, because TIF_NOTIFY_SIGNAL is handled on the way out to user
> mode, so a sibling applies the drop before executing any further
> userspace code. It does not synchronize against a sibling that is
> concurrently creating threads, so callers must keep the thread group
> quiescent while dropping.
>
> Measured with gVisor's "bounding set trimmed" boot phase on an arm64 KVM
> guest (medians over repeated boots):
> - 8 vCPUs: ~1.6ms -> ~0.10ms
> - 32 vCPUs: ~3.5ms -> ~0.11ms
> - 64 vCPUs: ~10.1ms -> ~0.1-0.6ms
> - cost goes from O(capabilities * threads) stop-the-world prctls to a
> single thread-group walk.
That is impressive, but please do detail the specific use case where
you need to drop from the bounding set after the go scheduler has started.
I can imagine some cases where you need to do some early setup and then
want to drop privileges, but you could also do that by re-exec'ing, so
I'd like to hear specifics.
This makes me nervous, reminding me of the 'sendmail capabilities bug'.
If some program specifically locks down one thread, I could imagine the
locked down thread forcing wrong behavior from the privileged threads
by calling this.
>
> Cc: Serge Hallyn <serge@hallyn.com>
> Cc: Paul Moore <paul@paul-moore.com>
> Cc: James Morris <jmorris@namei.org>
> Cc: Paul Walmsley <pjw@kernel.org>
> Cc: Thomas Gleixner <tglx@kernel.org>
> Cc: Zong Li <zong.li@sifive.com>
> Cc: Deepak Gupta <debug@rivosinc.com>
> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
> Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
> ---
> include/uapi/linux/prctl.h | 1 +
> security/commoncap.c | 129 +++++++++++++++++++++++++++++++++++++
> 2 files changed, 130 insertions(+)
>
> diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
> index b6ec6f693719..750a7824d3bc 100644
> --- a/include/uapi/linux/prctl.h
> +++ b/include/uapi/linux/prctl.h
> @@ -70,6 +70,7 @@
> /* Get/set the capability bounding set (as per security/commoncap.c) */
> #define PR_CAPBSET_READ 23
> #define PR_CAPBSET_DROP 24
> +#define PR_CAPBSET_DROP_MASK 83
>
> /* Get/set the process' ability to use the timestamp counter instruction */
> #define PR_GET_TSC 25
> diff --git a/security/commoncap.c b/security/commoncap.c
> index 3399535808fe..ae7ce50a8151 100644
> --- a/security/commoncap.c
> +++ b/security/commoncap.c
> @@ -19,7 +19,14 @@
> #include <linux/hugetlb.h>
> #include <linux/mount.h>
> #include <linux/sched.h>
> +#include <linux/cred.h>
> +#include <linux/rcupdate.h>
> +#include <linux/sched/signal.h>
> +#include <linux/sched/task.h>
> +#include <linux/slab.h>
> +#include <linux/task_work.h>
> #include <linux/prctl.h>
> +#include <linux/printk.h>
> #include <linux/securebits.h>
> #include <linux/user_namespace.h>
> #include <linux/binfmts.h>
> @@ -1283,6 +1290,123 @@ static int cap_prctl_drop(unsigned long cap)
> return commit_creds(new);
> }
>
> +/*
> + * Structure used to queue process-wide bounding set drops via task_work.
> + */
> +struct cap_bset_drop_work {
> + struct callback_head work;
> + struct task_struct *task;
> + kernel_cap_t mask;
> + struct cap_bset_drop_work *next;
> +};
> +
> +static void cap_bset_drop_work_fn(struct callback_head *work)
> +{
> + struct cap_bset_drop_work *w = container_of(work, struct cap_bset_drop_work, work);
> + struct cred *new = prepare_creds();
> +
> + if (!new) {
> + /* Out of memory: bounding set drop failed silently for this thread. */
> + pr_warn_ratelimited("capability bounding set drop failed for pid %d (%s)\n",
> + task_pid_nr(current), current->comm);
> + goto out;
> + }
> +
> + new->cap_bset = cap_drop(new->cap_bset, w->mask);
> + commit_creds(new);
> +
> +out:
> + put_task_struct(w->task);
> + kfree(w);
> +}
> +
> +/*
> + * cap_bset_drop_process - Drop capabilities from all threads in the group.
> + * @mask: Mask of capabilities to drop from the bounding set.
> + *
> + * Drops @mask from the calling thread synchronously, and queues a task_work
> + * item for each sibling thread to safely apply the drop in its own context.
> + *
> + * The caller must hold CAP_SETPCAP. Thread group must be quiescent to avoid
> + * racing with concurrent thread creation.
> + *
> + * Returns 0 on success, or -ENOMEM if allocations fail (all-or-nothing).
> + */
> +static int cap_bset_drop_process(kernel_cap_t mask)
> +{
> + struct cap_bset_drop_work *list = NULL, *w, *next;
> + struct task_struct *thread;
> + struct cred *new = NULL;
> + int ret = 0;
> +
> + rcu_read_lock();
> + for_each_thread(current, thread) {
> + const struct cred *cred;
> +
> + if (thread == current || (thread->flags & PF_EXITING))
> + continue;
> +
> + cred = __task_cred(thread);
> + if (cap_isclear(cap_intersect(cred->cap_bset, mask)))
> + continue;
> +
> + w = kmalloc_obj(*w, GFP_ATOMIC);
> + if (!w) {
> + ret = -ENOMEM;
> + break;
> + }
> +
> + w->task = get_task_struct(thread);
> + w->mask = mask;
> + w->next = list;
> + list = w;
> + }
> + rcu_read_unlock();
> +
> + if (!ret) {
> + new = prepare_creds();
> + if (!new)
> + ret = -ENOMEM;
> + }
> +
> + if (ret) {
> + while (list) {
> + next = list->next;
> + put_task_struct(list->task);
> + kfree(list);
> + list = next;
> + }
> + return ret;
> + }
> +
> + for (w = list; w; w = next) {
> + next = w->next;
> + init_task_work(&w->work, cap_bset_drop_work_fn);
> + if (task_work_add(w->task, &w->work, TWA_SIGNAL)) {
> + put_task_struct(w->task);
> + kfree(w);
> + }
> + }
> +
> + new->cap_bset = cap_drop(new->cap_bset, mask);
> + commit_creds(new);
> +
> + return 0;
> +}
> +
> +static int cap_prctl_drop_mask(unsigned long low, unsigned long high)
> +{
> + kernel_cap_t mask = mk_kernel_cap((u32)low, (u32)high);
> +
> + if (cap_isclear(mask))
> + return 0;
> +
> + if (!ns_capable(current_user_ns(), CAP_SETPCAP))
> + return -EPERM;
> +
> + return cap_bset_drop_process(mask);
> +}
> +
> /**
> * cap_task_prctl - Implement process control functions for this security module
> * @option: The process control function requested
> @@ -1313,6 +1437,11 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
> case PR_CAPBSET_DROP:
> return cap_prctl_drop(arg2);
>
> + case PR_CAPBSET_DROP_MASK:
> + if (arg4 || arg5)
> + return -EINVAL;
> + return cap_prctl_drop_mask(arg2, arg3);
> +
> /*
> * The next four prctl's remain to assist with transitioning a
> * system from legacy UID=0 based privilege (when filesystem
> --
> 2.34.1
在 2026/9/23 1:01, Serge E. Hallyn 写道:
> On Tue, Sep 22, 2026 at 05:58:16PM +0800, Jinjie Ruan wrote:
>> The capability bounding set is per-thread: PR_CAPBSET_DROP only affects
>> the calling thread, since its bounding set lives in the per-task struct
>> cred. User space that wants to drop capabilities for a whole process
>> must therefore invoke PR_CAPBSET_DROP once per capability per thread,
>> which on a many-threaded process is expensive, and from a Go runtime
>> requires stopping the world and signalling every thread.
>>
>> Add PR_CAPBSET_DROP_MASK, an opt-in prctl that removes a set of
>> capabilities, given as a 64-bit mask in arg2 (low 32 bits) and arg3
>> (high 32 bits), from the bounding set of every thread of the calling
>> thread group in a single call.
>>
>> The calling thread drops the capabilities synchronously, last; every
>> sibling that still holds any of them is asked to drop them through a
>> task_work item, so that it applies the drop in its own context. This
>> avoids racing with a sibling's concurrent credential updates such as
>> setuid() or capset(). The call does not wait for the siblings: a
>> sibling may be parked in a wait that is not woken by TIF_NOTIFY_SIGNAL
>> (e.g. futex), so waiting could block for an unbounded time. This is
>> still safe, because TIF_NOTIFY_SIGNAL is handled on the way out to user
>> mode, so a sibling applies the drop before executing any further
>> userspace code. It does not synchronize against a sibling that is
>> concurrently creating threads, so callers must keep the thread group
>> quiescent while dropping.
>>
>> Measured with gVisor's "bounding set trimmed" boot phase on an arm64 KVM
>> guest (medians over repeated boots):
>> - 8 vCPUs: ~1.6ms -> ~0.10ms
>> - 32 vCPUs: ~3.5ms -> ~0.11ms
>> - 64 vCPUs: ~10.1ms -> ~0.1-0.6ms
>> - cost goes from O(capabilities * threads) stop-the-world prctls to a
>> single thread-group walk.
>
> That is impressive, but please do detail the specific use case where
> you need to drop from the bounding set after the go scheduler has started.
> I can imagine some cases where you need to do some early setup and then
> want to drop privileges, but you could also do that by re-exec'ing, so
> I'd like to hear specifics.
Hi Serge,
Thanks for the review.
The use case is gVisor's sentry: a long-lived, pure-Go process that
starts a sandbox per container/pod. The final capability set depends on
the spec, the platform (ptrace requires CAP_SYS_PTRACE),
directfs/networking, and the capabilities granted to the runtime's user
namespace.
It is therefore only known after the runtime and gVisor's own threads
are already up — the trim happens multi-threaded. We do have a re-exec
path, but it re-loads a ~100 MB binary and re-runs Go init, so we only
take it when forced.
>
> This makes me nervous, reminding me of the 'sendmail capabilities bug'.
> If some program specifically locks down one thread, I could imagine the
> locked down thread forcing wrong behavior from the privileged threads
> by calling this.
Fair concern. This new prcoess-wide drop is also a drop — it only
removes capabilities from all threads, and requires CAP_SETPCAP. But it
must actually reach every thread, so the thread-creation race still
needs to be addressed.
>
>>
>> Cc: Serge Hallyn <serge@hallyn.com>
>> Cc: Paul Moore <paul@paul-moore.com>
>> Cc: James Morris <jmorris@namei.org>
>> Cc: Paul Walmsley <pjw@kernel.org>
>> Cc: Thomas Gleixner <tglx@kernel.org>
>> Cc: Zong Li <zong.li@sifive.com>
>> Cc: Deepak Gupta <debug@rivosinc.com>
>> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
>> Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
>> ---
>> include/uapi/linux/prctl.h | 1 +
>> security/commoncap.c | 129 +++++++++++++++++++++++++++++++++++++
>> 2 files changed, 130 insertions(+)
>>
>> diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
>> index b6ec6f693719..750a7824d3bc 100644
>> --- a/include/uapi/linux/prctl.h
>> +++ b/include/uapi/linux/prctl.h
>> @@ -70,6 +70,7 @@
>> /* Get/set the capability bounding set (as per security/commoncap.c) */
>> #define PR_CAPBSET_READ 23
>> #define PR_CAPBSET_DROP 24
>> +#define PR_CAPBSET_DROP_MASK 83
>>
>> /* Get/set the process' ability to use the timestamp counter instruction */
>> #define PR_GET_TSC 25
>> diff --git a/security/commoncap.c b/security/commoncap.c
>> index 3399535808fe..ae7ce50a8151 100644
>> --- a/security/commoncap.c
>> +++ b/security/commoncap.c
>> @@ -19,7 +19,14 @@
>> #include <linux/hugetlb.h>
>> #include <linux/mount.h>
>> #include <linux/sched.h>
>> +#include <linux/cred.h>
>> +#include <linux/rcupdate.h>
>> +#include <linux/sched/signal.h>
>> +#include <linux/sched/task.h>
>> +#include <linux/slab.h>
>> +#include <linux/task_work.h>
>> #include <linux/prctl.h>
>> +#include <linux/printk.h>
>> #include <linux/securebits.h>
>> #include <linux/user_namespace.h>
>> #include <linux/binfmts.h>
>> @@ -1283,6 +1290,123 @@ static int cap_prctl_drop(unsigned long cap)
>> return commit_creds(new);
>> }
>>
>> +/*
>> + * Structure used to queue process-wide bounding set drops via task_work.
>> + */
>> +struct cap_bset_drop_work {
>> + struct callback_head work;
>> + struct task_struct *task;
>> + kernel_cap_t mask;
>> + struct cap_bset_drop_work *next;
>> +};
>> +
>> +static void cap_bset_drop_work_fn(struct callback_head *work)
>> +{
>> + struct cap_bset_drop_work *w = container_of(work, struct cap_bset_drop_work, work);
>> + struct cred *new = prepare_creds();
>> +
>> + if (!new) {
>> + /* Out of memory: bounding set drop failed silently for this thread. */
>> + pr_warn_ratelimited("capability bounding set drop failed for pid %d (%s)\n",
>> + task_pid_nr(current), current->comm);
>> + goto out;
>> + }
>> +
>> + new->cap_bset = cap_drop(new->cap_bset, w->mask);
>> + commit_creds(new);
>> +
>> +out:
>> + put_task_struct(w->task);
>> + kfree(w);
>> +}
>> +
>> +/*
>> + * cap_bset_drop_process - Drop capabilities from all threads in the group.
>> + * @mask: Mask of capabilities to drop from the bounding set.
>> + *
>> + * Drops @mask from the calling thread synchronously, and queues a task_work
>> + * item for each sibling thread to safely apply the drop in its own context.
>> + *
>> + * The caller must hold CAP_SETPCAP. Thread group must be quiescent to avoid
>> + * racing with concurrent thread creation.
>> + *
>> + * Returns 0 on success, or -ENOMEM if allocations fail (all-or-nothing).
>> + */
>> +static int cap_bset_drop_process(kernel_cap_t mask)
>> +{
>> + struct cap_bset_drop_work *list = NULL, *w, *next;
>> + struct task_struct *thread;
>> + struct cred *new = NULL;
>> + int ret = 0;
>> +
>> + rcu_read_lock();
>> + for_each_thread(current, thread) {
>> + const struct cred *cred;
>> +
>> + if (thread == current || (thread->flags & PF_EXITING))
>> + continue;
>> +
>> + cred = __task_cred(thread);
>> + if (cap_isclear(cap_intersect(cred->cap_bset, mask)))
>> + continue;
>> +
>> + w = kmalloc_obj(*w, GFP_ATOMIC);
>> + if (!w) {
>> + ret = -ENOMEM;
>> + break;
>> + }
>> +
>> + w->task = get_task_struct(thread);
>> + w->mask = mask;
>> + w->next = list;
>> + list = w;
>> + }
>> + rcu_read_unlock();
>> +
>> + if (!ret) {
>> + new = prepare_creds();
>> + if (!new)
>> + ret = -ENOMEM;
>> + }
>> +
>> + if (ret) {
>> + while (list) {
>> + next = list->next;
>> + put_task_struct(list->task);
>> + kfree(list);
>> + list = next;
>> + }
>> + return ret;
>> + }
>> +
>> + for (w = list; w; w = next) {
>> + next = w->next;
>> + init_task_work(&w->work, cap_bset_drop_work_fn);
>> + if (task_work_add(w->task, &w->work, TWA_SIGNAL)) {
>> + put_task_struct(w->task);
>> + kfree(w);
>> + }
>> + }
>> +
>> + new->cap_bset = cap_drop(new->cap_bset, mask);
>> + commit_creds(new);
>> +
>> + return 0;
>> +}
>> +
>> +static int cap_prctl_drop_mask(unsigned long low, unsigned long high)
>> +{
>> + kernel_cap_t mask = mk_kernel_cap((u32)low, (u32)high);
>> +
>> + if (cap_isclear(mask))
>> + return 0;
>> +
>> + if (!ns_capable(current_user_ns(), CAP_SETPCAP))
>> + return -EPERM;
>> +
>> + return cap_bset_drop_process(mask);
>> +}
>> +
>> /**
>> * cap_task_prctl - Implement process control functions for this security module
>> * @option: The process control function requested
>> @@ -1313,6 +1437,11 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
>> case PR_CAPBSET_DROP:
>> return cap_prctl_drop(arg2);
>>
>> + case PR_CAPBSET_DROP_MASK:
>> + if (arg4 || arg5)
>> + return -EINVAL;
>> + return cap_prctl_drop_mask(arg2, arg3);
>> +
>> /*
>> * The next four prctl's remain to assist with transitioning a
>> * system from legacy UID=0 based privilege (when filesystem
>> --
>> 2.34.1
--
Best regards,
Jinjie
The https://pkg.go.dev/kernel.org/pub/linux/libs/security/libcap/cap#IAB.SetProc
already handles this for the whole process. It can be run from main()
if you need it to happen early, and it will track down all of the
threads in the runtime.
To Serge's point, I am also curious what benefit there is from doing
it more quickly. After all, this is pretty much a one-time function
request for any executable.
FYI The "sendmail capabilities bug" reference is written up here:
https://sites.google.com/site/fullycapable/thesendmailcapabilitiesissue
Cheers
Andrew
On Tue, Sep 22, 2026 at 10:01 AM Serge E. Hallyn <serge@hallyn.com> wrote:
>
> On Tue, Sep 22, 2026 at 05:58:16PM +0800, Jinjie Ruan wrote:
> > The capability bounding set is per-thread: PR_CAPBSET_DROP only affects
> > the calling thread, since its bounding set lives in the per-task struct
> > cred. User space that wants to drop capabilities for a whole process
> > must therefore invoke PR_CAPBSET_DROP once per capability per thread,
> > which on a many-threaded process is expensive, and from a Go runtime
> > requires stopping the world and signalling every thread.
> >
> > Add PR_CAPBSET_DROP_MASK, an opt-in prctl that removes a set of
> > capabilities, given as a 64-bit mask in arg2 (low 32 bits) and arg3
> > (high 32 bits), from the bounding set of every thread of the calling
> > thread group in a single call.
> >
> > The calling thread drops the capabilities synchronously, last; every
> > sibling that still holds any of them is asked to drop them through a
> > task_work item, so that it applies the drop in its own context. This
> > avoids racing with a sibling's concurrent credential updates such as
> > setuid() or capset(). The call does not wait for the siblings: a
> > sibling may be parked in a wait that is not woken by TIF_NOTIFY_SIGNAL
> > (e.g. futex), so waiting could block for an unbounded time. This is
> > still safe, because TIF_NOTIFY_SIGNAL is handled on the way out to user
> > mode, so a sibling applies the drop before executing any further
> > userspace code. It does not synchronize against a sibling that is
> > concurrently creating threads, so callers must keep the thread group
> > quiescent while dropping.
> >
> > Measured with gVisor's "bounding set trimmed" boot phase on an arm64 KVM
> > guest (medians over repeated boots):
> > - 8 vCPUs: ~1.6ms -> ~0.10ms
> > - 32 vCPUs: ~3.5ms -> ~0.11ms
> > - 64 vCPUs: ~10.1ms -> ~0.1-0.6ms
> > - cost goes from O(capabilities * threads) stop-the-world prctls to a
> > single thread-group walk.
>
> That is impressive, but please do detail the specific use case where
> you need to drop from the bounding set after the go scheduler has started.
> I can imagine some cases where you need to do some early setup and then
> want to drop privileges, but you could also do that by re-exec'ing, so
> I'd like to hear specifics.
>
> This makes me nervous, reminding me of the 'sendmail capabilities bug'.
> If some program specifically locks down one thread, I could imagine the
> locked down thread forcing wrong behavior from the privileged threads
> by calling this.
>
> >
> > Cc: Serge Hallyn <serge@hallyn.com>
> > Cc: Paul Moore <paul@paul-moore.com>
> > Cc: James Morris <jmorris@namei.org>
> > Cc: Paul Walmsley <pjw@kernel.org>
> > Cc: Thomas Gleixner <tglx@kernel.org>
> > Cc: Zong Li <zong.li@sifive.com>
> > Cc: Deepak Gupta <debug@rivosinc.com>
> > Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
> > Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
> > ---
> > include/uapi/linux/prctl.h | 1 +
> > security/commoncap.c | 129 +++++++++++++++++++++++++++++++++++++
> > 2 files changed, 130 insertions(+)
> >
> > diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
> > index b6ec6f693719..750a7824d3bc 100644
> > --- a/include/uapi/linux/prctl.h
> > +++ b/include/uapi/linux/prctl.h
> > @@ -70,6 +70,7 @@
> > /* Get/set the capability bounding set (as per security/commoncap.c) */
> > #define PR_CAPBSET_READ 23
> > #define PR_CAPBSET_DROP 24
> > +#define PR_CAPBSET_DROP_MASK 83
> >
> > /* Get/set the process' ability to use the timestamp counter instruction */
> > #define PR_GET_TSC 25
> > diff --git a/security/commoncap.c b/security/commoncap.c
> > index 3399535808fe..ae7ce50a8151 100644
> > --- a/security/commoncap.c
> > +++ b/security/commoncap.c
> > @@ -19,7 +19,14 @@
> > #include <linux/hugetlb.h>
> > #include <linux/mount.h>
> > #include <linux/sched.h>
> > +#include <linux/cred.h>
> > +#include <linux/rcupdate.h>
> > +#include <linux/sched/signal.h>
> > +#include <linux/sched/task.h>
> > +#include <linux/slab.h>
> > +#include <linux/task_work.h>
> > #include <linux/prctl.h>
> > +#include <linux/printk.h>
> > #include <linux/securebits.h>
> > #include <linux/user_namespace.h>
> > #include <linux/binfmts.h>
> > @@ -1283,6 +1290,123 @@ static int cap_prctl_drop(unsigned long cap)
> > return commit_creds(new);
> > }
> >
> > +/*
> > + * Structure used to queue process-wide bounding set drops via task_work.
> > + */
> > +struct cap_bset_drop_work {
> > + struct callback_head work;
> > + struct task_struct *task;
> > + kernel_cap_t mask;
> > + struct cap_bset_drop_work *next;
> > +};
> > +
> > +static void cap_bset_drop_work_fn(struct callback_head *work)
> > +{
> > + struct cap_bset_drop_work *w = container_of(work, struct cap_bset_drop_work, work);
> > + struct cred *new = prepare_creds();
> > +
> > + if (!new) {
> > + /* Out of memory: bounding set drop failed silently for this thread. */
> > + pr_warn_ratelimited("capability bounding set drop failed for pid %d (%s)\n",
> > + task_pid_nr(current), current->comm);
> > + goto out;
> > + }
> > +
> > + new->cap_bset = cap_drop(new->cap_bset, w->mask);
> > + commit_creds(new);
> > +
> > +out:
> > + put_task_struct(w->task);
> > + kfree(w);
> > +}
> > +
> > +/*
> > + * cap_bset_drop_process - Drop capabilities from all threads in the group.
> > + * @mask: Mask of capabilities to drop from the bounding set.
> > + *
> > + * Drops @mask from the calling thread synchronously, and queues a task_work
> > + * item for each sibling thread to safely apply the drop in its own context.
> > + *
> > + * The caller must hold CAP_SETPCAP. Thread group must be quiescent to avoid
> > + * racing with concurrent thread creation.
> > + *
> > + * Returns 0 on success, or -ENOMEM if allocations fail (all-or-nothing).
> > + */
> > +static int cap_bset_drop_process(kernel_cap_t mask)
> > +{
> > + struct cap_bset_drop_work *list = NULL, *w, *next;
> > + struct task_struct *thread;
> > + struct cred *new = NULL;
> > + int ret = 0;
> > +
> > + rcu_read_lock();
> > + for_each_thread(current, thread) {
> > + const struct cred *cred;
> > +
> > + if (thread == current || (thread->flags & PF_EXITING))
> > + continue;
> > +
> > + cred = __task_cred(thread);
> > + if (cap_isclear(cap_intersect(cred->cap_bset, mask)))
> > + continue;
> > +
> > + w = kmalloc_obj(*w, GFP_ATOMIC);
> > + if (!w) {
> > + ret = -ENOMEM;
> > + break;
> > + }
> > +
> > + w->task = get_task_struct(thread);
> > + w->mask = mask;
> > + w->next = list;
> > + list = w;
> > + }
> > + rcu_read_unlock();
> > +
> > + if (!ret) {
> > + new = prepare_creds();
> > + if (!new)
> > + ret = -ENOMEM;
> > + }
> > +
> > + if (ret) {
> > + while (list) {
> > + next = list->next;
> > + put_task_struct(list->task);
> > + kfree(list);
> > + list = next;
> > + }
> > + return ret;
> > + }
> > +
> > + for (w = list; w; w = next) {
> > + next = w->next;
> > + init_task_work(&w->work, cap_bset_drop_work_fn);
> > + if (task_work_add(w->task, &w->work, TWA_SIGNAL)) {
> > + put_task_struct(w->task);
> > + kfree(w);
> > + }
> > + }
> > +
> > + new->cap_bset = cap_drop(new->cap_bset, mask);
> > + commit_creds(new);
> > +
> > + return 0;
> > +}
> > +
> > +static int cap_prctl_drop_mask(unsigned long low, unsigned long high)
> > +{
> > + kernel_cap_t mask = mk_kernel_cap((u32)low, (u32)high);
> > +
> > + if (cap_isclear(mask))
> > + return 0;
> > +
> > + if (!ns_capable(current_user_ns(), CAP_SETPCAP))
> > + return -EPERM;
> > +
> > + return cap_bset_drop_process(mask);
> > +}
> > +
> > /**
> > * cap_task_prctl - Implement process control functions for this security module
> > * @option: The process control function requested
> > @@ -1313,6 +1437,11 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
> > case PR_CAPBSET_DROP:
> > return cap_prctl_drop(arg2);
> >
> > + case PR_CAPBSET_DROP_MASK:
> > + if (arg4 || arg5)
> > + return -EINVAL;
> > + return cap_prctl_drop_mask(arg2, arg3);
> > +
> > /*
> > * The next four prctl's remain to assist with transitioning a
> > * system from legacy UID=0 based privilege (when filesystem
> > --
> > 2.34.1
在 2026/9/23 10:10, Andrew G. Morgan 写道:
> The https://pkg.go.dev/kernel.org/pub/linux/libs/security/libcap/cap#IAB.SetProc
> already handles this for the whole process. It can be run from main()
I think libcap argues *for* a kernel primitive here.
Its docs say whole-process (POSIX) semantics are implemented via
`libcap/psx`, which uses `syscall.AllThreadsSyscall()` when available,
and it exports `Prctlw` ("executes on all the threads of the process").
So `IAB.SetProc` does the same per-thread prctl dance as gvisor do
below— it doesn't avoid the cost.
112 // Apply applies `r` to every thread of the current process.
113 // May be run without procfs available.
114 // Fails with `ENOTSUP` in cgo builds.
115 func (r *ResolvedThreadCaps) Apply(timer *timing.Timer) error {
116 >-------// 1. Trim the bounding set on every thread. This must
happen before
117 >-------// capset drops CAP_SETPCAP from the effective set
(PR_CAPBSET_DROP
118 >-------// requires it).
119 >-------if r.haveSetPCap {
120 >------->-------for c := capability.Cap(0); c <= r.lastCap; c++ {
121 >------->------->-------if r.bounding&(uint64(1)<<uint(c)) != 0 {
122 >------->------->------->-------continue
123 >------->------->-------}
124 >------->------->-------if err :=
allThreadsPrctl(unix.PR_CAPBSET_DROP, uintptr(c), 0); err != nil {
125 >------->------->------->-------return fmt.Errorf("dropping bounding
capability %v on all threads: %w", c, err)
126 >------->------->-------}
127 >------->-------}
128 >-------}
58 // allThreadsPrctl issues `prctl(option, arg2, arg3)` on every OS
thread of the
59 // process via `syscall.AllThreadsSyscall6`.
60 func allThreadsPrctl(option, arg2, arg3 uintptr) error {
61 >-------// EINVAL is ignored to mirror `capability.Apply`'s handling
of unsupported caps.
62 >-------if _, _, errno := syscall.AllThreadsSyscall6(unix.SYS_PRCTL,
option, arg2, arg3, 0, 0, 0); errno != 0 && err no != unix.EINVAL {
63 >------->-------return errno
64 >-------}
65 >-------return nil
66 }
> if you need it to happen early, and it will track down all of the
> threads in the runtime.
>
> To Serge's point, I am also curious what benefit there is from doing
> it more quickly. After all, this is pretty much a one-time function
> request for any executable.
Every cap drop across all threads requires pausing each thread to
deliver a signal and resume it — effectively stop-the-world signal
delivery per thread, which serializes the operation and can't be
parallelized across cores.
The bounding-set trim is the worst case. As the code shows,
PR_CAPBSET_DROP must run per-thread for each capability bit.
So it's N threads × M capability bits stop-and-resume operations, all
serialized.
The benefit of doing this faster isn't about a one-time cost — gVisor
starts a sandbox per container and an agent starts a fresh sandbox per
task, so this runs on every sandbox start. And the local test shows that
warm end-to-end startup is ~160 ms (sentry boot ~70 ms), and the ~10 ms
trim on a high-core host is ~6% of end-to-end and ~14% of the sentry
boot — the largest single syscall phase in early boot. That's the hot
path, which is why making it faster matters.
>
> FYI The "sendmail capabilities bug" reference is written up here:
> https://sites.google.com/site/fullycapable/thesendmailcapabilitiesissue
>
> Cheers
>
> Andrew
>
> On Tue, Sep 22, 2026 at 10:01 AM Serge E. Hallyn <serge@hallyn.com> wrote:
>>
>> On Tue, Sep 22, 2026 at 05:58:16PM +0800, Jinjie Ruan wrote:
>>> The capability bounding set is per-thread: PR_CAPBSET_DROP only affects
>>> the calling thread, since its bounding set lives in the per-task struct
>>> cred. User space that wants to drop capabilities for a whole process
>>> must therefore invoke PR_CAPBSET_DROP once per capability per thread,
>>> which on a many-threaded process is expensive, and from a Go runtime
>>> requires stopping the world and signalling every thread.
>>>
>>> Add PR_CAPBSET_DROP_MASK, an opt-in prctl that removes a set of
>>> capabilities, given as a 64-bit mask in arg2 (low 32 bits) and arg3
>>> (high 32 bits), from the bounding set of every thread of the calling
>>> thread group in a single call.
>>>
>>> The calling thread drops the capabilities synchronously, last; every
>>> sibling that still holds any of them is asked to drop them through a
>>> task_work item, so that it applies the drop in its own context. This
>>> avoids racing with a sibling's concurrent credential updates such as
>>> setuid() or capset(). The call does not wait for the siblings: a
>>> sibling may be parked in a wait that is not woken by TIF_NOTIFY_SIGNAL
>>> (e.g. futex), so waiting could block for an unbounded time. This is
>>> still safe, because TIF_NOTIFY_SIGNAL is handled on the way out to user
>>> mode, so a sibling applies the drop before executing any further
>>> userspace code. It does not synchronize against a sibling that is
>>> concurrently creating threads, so callers must keep the thread group
>>> quiescent while dropping.
>>>
>>> Measured with gVisor's "bounding set trimmed" boot phase on an arm64 KVM
>>> guest (medians over repeated boots):
>>> - 8 vCPUs: ~1.6ms -> ~0.10ms
>>> - 32 vCPUs: ~3.5ms -> ~0.11ms
>>> - 64 vCPUs: ~10.1ms -> ~0.1-0.6ms
>>> - cost goes from O(capabilities * threads) stop-the-world prctls to a
>>> single thread-group walk.
>>
>> That is impressive, but please do detail the specific use case where
>> you need to drop from the bounding set after the go scheduler has started.
>> I can imagine some cases where you need to do some early setup and then
>> want to drop privileges, but you could also do that by re-exec'ing, so
>> I'd like to hear specifics.
>>
>> This makes me nervous, reminding me of the 'sendmail capabilities bug'.
>> If some program specifically locks down one thread, I could imagine the
>> locked down thread forcing wrong behavior from the privileged threads
>> by calling this.
>>
>>>
>>> Cc: Serge Hallyn <serge@hallyn.com>
>>> Cc: Paul Moore <paul@paul-moore.com>
>>> Cc: James Morris <jmorris@namei.org>
>>> Cc: Paul Walmsley <pjw@kernel.org>
>>> Cc: Thomas Gleixner <tglx@kernel.org>
>>> Cc: Zong Li <zong.li@sifive.com>
>>> Cc: Deepak Gupta <debug@rivosinc.com>
>>> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
>>> Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
>>> ---
>>> include/uapi/linux/prctl.h | 1 +
>>> security/commoncap.c | 129 +++++++++++++++++++++++++++++++++++++
>>> 2 files changed, 130 insertions(+)
>>>
>>> diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h
>>> index b6ec6f693719..750a7824d3bc 100644
>>> --- a/include/uapi/linux/prctl.h
>>> +++ b/include/uapi/linux/prctl.h
>>> @@ -70,6 +70,7 @@
>>> /* Get/set the capability bounding set (as per security/commoncap.c) */
>>> #define PR_CAPBSET_READ 23
>>> #define PR_CAPBSET_DROP 24
>>> +#define PR_CAPBSET_DROP_MASK 83
>>>
>>> /* Get/set the process' ability to use the timestamp counter instruction */
>>> #define PR_GET_TSC 25
>>> diff --git a/security/commoncap.c b/security/commoncap.c
>>> index 3399535808fe..ae7ce50a8151 100644
>>> --- a/security/commoncap.c
>>> +++ b/security/commoncap.c
>>> @@ -19,7 +19,14 @@
>>> #include <linux/hugetlb.h>
>>> #include <linux/mount.h>
>>> #include <linux/sched.h>
>>> +#include <linux/cred.h>
>>> +#include <linux/rcupdate.h>
>>> +#include <linux/sched/signal.h>
>>> +#include <linux/sched/task.h>
>>> +#include <linux/slab.h>
>>> +#include <linux/task_work.h>
>>> #include <linux/prctl.h>
>>> +#include <linux/printk.h>
>>> #include <linux/securebits.h>
>>> #include <linux/user_namespace.h>
>>> #include <linux/binfmts.h>
>>> @@ -1283,6 +1290,123 @@ static int cap_prctl_drop(unsigned long cap)
>>> return commit_creds(new);
>>> }
>>>
>>> +/*
>>> + * Structure used to queue process-wide bounding set drops via task_work.
>>> + */
>>> +struct cap_bset_drop_work {
>>> + struct callback_head work;
>>> + struct task_struct *task;
>>> + kernel_cap_t mask;
>>> + struct cap_bset_drop_work *next;
>>> +};
>>> +
>>> +static void cap_bset_drop_work_fn(struct callback_head *work)
>>> +{
>>> + struct cap_bset_drop_work *w = container_of(work, struct cap_bset_drop_work, work);
>>> + struct cred *new = prepare_creds();
>>> +
>>> + if (!new) {
>>> + /* Out of memory: bounding set drop failed silently for this thread. */
>>> + pr_warn_ratelimited("capability bounding set drop failed for pid %d (%s)\n",
>>> + task_pid_nr(current), current->comm);
>>> + goto out;
>>> + }
>>> +
>>> + new->cap_bset = cap_drop(new->cap_bset, w->mask);
>>> + commit_creds(new);
>>> +
>>> +out:
>>> + put_task_struct(w->task);
>>> + kfree(w);
>>> +}
>>> +
>>> +/*
>>> + * cap_bset_drop_process - Drop capabilities from all threads in the group.
>>> + * @mask: Mask of capabilities to drop from the bounding set.
>>> + *
>>> + * Drops @mask from the calling thread synchronously, and queues a task_work
>>> + * item for each sibling thread to safely apply the drop in its own context.
>>> + *
>>> + * The caller must hold CAP_SETPCAP. Thread group must be quiescent to avoid
>>> + * racing with concurrent thread creation.
>>> + *
>>> + * Returns 0 on success, or -ENOMEM if allocations fail (all-or-nothing).
>>> + */
>>> +static int cap_bset_drop_process(kernel_cap_t mask)
>>> +{
>>> + struct cap_bset_drop_work *list = NULL, *w, *next;
>>> + struct task_struct *thread;
>>> + struct cred *new = NULL;
>>> + int ret = 0;
>>> +
>>> + rcu_read_lock();
>>> + for_each_thread(current, thread) {
>>> + const struct cred *cred;
>>> +
>>> + if (thread == current || (thread->flags & PF_EXITING))
>>> + continue;
>>> +
>>> + cred = __task_cred(thread);
>>> + if (cap_isclear(cap_intersect(cred->cap_bset, mask)))
>>> + continue;
>>> +
>>> + w = kmalloc_obj(*w, GFP_ATOMIC);
>>> + if (!w) {
>>> + ret = -ENOMEM;
>>> + break;
>>> + }
>>> +
>>> + w->task = get_task_struct(thread);
>>> + w->mask = mask;
>>> + w->next = list;
>>> + list = w;
>>> + }
>>> + rcu_read_unlock();
>>> +
>>> + if (!ret) {
>>> + new = prepare_creds();
>>> + if (!new)
>>> + ret = -ENOMEM;
>>> + }
>>> +
>>> + if (ret) {
>>> + while (list) {
>>> + next = list->next;
>>> + put_task_struct(list->task);
>>> + kfree(list);
>>> + list = next;
>>> + }
>>> + return ret;
>>> + }
>>> +
>>> + for (w = list; w; w = next) {
>>> + next = w->next;
>>> + init_task_work(&w->work, cap_bset_drop_work_fn);
>>> + if (task_work_add(w->task, &w->work, TWA_SIGNAL)) {
>>> + put_task_struct(w->task);
>>> + kfree(w);
>>> + }
>>> + }
>>> +
>>> + new->cap_bset = cap_drop(new->cap_bset, mask);
>>> + commit_creds(new);
>>> +
>>> + return 0;
>>> +}
>>> +
>>> +static int cap_prctl_drop_mask(unsigned long low, unsigned long high)
>>> +{
>>> + kernel_cap_t mask = mk_kernel_cap((u32)low, (u32)high);
>>> +
>>> + if (cap_isclear(mask))
>>> + return 0;
>>> +
>>> + if (!ns_capable(current_user_ns(), CAP_SETPCAP))
>>> + return -EPERM;
>>> +
>>> + return cap_bset_drop_process(mask);
>>> +}
>>> +
>>> /**
>>> * cap_task_prctl - Implement process control functions for this security module
>>> * @option: The process control function requested
>>> @@ -1313,6 +1437,11 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
>>> case PR_CAPBSET_DROP:
>>> return cap_prctl_drop(arg2);
>>>
>>> + case PR_CAPBSET_DROP_MASK:
>>> + if (arg4 || arg5)
>>> + return -EINVAL;
>>> + return cap_prctl_drop_mask(arg2, arg3);
>>> +
>>> /*
>>> * The next four prctl's remain to assist with transitioning a
>>> * system from legacy UID=0 based privilege (when filesystem
>>> --
>>> 2.34.1
--
Best regards,
Jinjie
© 2016 - 2026 Red Hat, Inc.